ningyao-voice-launcherInstall and configure a local browser-based Chinese voice chat launcher with the Ning Yao persona, including one-click Windows launchers, browser speech I/O,...
Install via ClawdBot CLI:
clawdbot install jiwannian/ningyao-voice-launcherGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAICalls external URL not in known-safe list
https://registry.npmmirror.com/@types/node/-/node-18.19.130.tgzUses known external API (expected, informational)
api.openai.comAI Analysis
The skill's primary function is to install and configure a local application that interacts with the user's specified OpenAI API endpoint, which is consistent with its stated purpose. The external npm registry call is a standard part of dependency installation, and while credential access is noted, it is for the user's own API key to enable the core functionality, not for harvesting. No hidden instructions, obfuscation, or unauthorized data exfiltration patterns were identified in the provided definition.
Generated Mar 21, 2026
Individuals seeking a local, privacy-focused voice chat companion can install this launcher to interact with the Ning Yao persona via voice. It's ideal for users who prefer avoiding cloud-based assistants and want a customizable, offline-capable interaction experience.
Developers working on voice-enabled applications can use this package as a template to quickly deploy a local voice chat system with screen awareness. It simplifies integration of OpenAI's vision models for testing multimodal interactions in a controlled environment.
Educators or language learners can configure the launcher with a persona prompt tailored for language practice, enabling interactive voice conversations in Chinese. The local setup ensures data privacy and reduces latency for real-time speech feedback.
Users with mobility or visual impairments can deploy this launcher as a voice-controlled interface for computer tasks, leveraging screen analysis to interpret on-screen content. It provides a safe, restricted terminal for basic commands without full system access.
Offer the basic launcher for free, then charge for advanced features like custom persona tuning, extended screen analysis capabilities, or priority support. This model attracts hobbyists while monetizing power users and enterprises.
License the launcher technology to businesses for embedding into their products, such as customer service bots or internal tools. Provide customization services and API access for seamless integration with existing systems.
Partner with hardware manufacturers to pre-install the launcher on devices like smart speakers or kiosks, targeting markets interested in localized voice assistants. Offer ongoing updates and support as part of the bundle.
💬 Integration Tip
Ensure Chrome or Edge is used for optimal speech recognition, and configure the .env file with a valid OpenAI API key and model supporting vision if screen analysis is needed.
Scored Apr 19, 2026
Audited Apr 17, 2026 · audit v1.0
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...